Update app.py

app.py

@@ -26,7 +26,7 @@ def chat_with_bot(user_input, history):
         prompt += f"User: {user}\nAssistant: {bot}\n"
     prompt += f"User: {user_input}\nAssistant:"
 
-    inputs = tokenizer(prompt, return_tensors="pt").to("cpu")
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
     outputs = model.generate(
         **inputs,
         max_new_tokens=256,